Opendata, web and dolomites


High-level Prior Models for Computer Vision

Total Cost €


EC-Contrib. €






Project "HOMOVIS" data sheet

The following table provides information about the project.


Organization address
city: GRAZ
postcode: 8010

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country Austria [AT]
 Project website
 Total cost 1˙473˙525 €
 EC max contribution 1˙473˙525 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2014-STG
 Funding Scheme ERC-STG
 Starting year 2015
 Duration (year-month-day) from 2015-06-01   to  2020-05-31


Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    TECHNISCHE UNIVERSITAET GRAZ AT (GRAZ) coordinator 1˙473˙525.00


 Project objective

Since more than 50 years, computer vision has been a very active research field but it is still far away from the abilities of the human visual system. This stunning performance of the human visual system can be mainly contributed to a highly efficient three-layer architecture: A low-level layer that sparsifies the visual information by detecting important image features such as image gradients, a mid-level layer that implements disocclusion and boundary completion processes and finally a high-level layer that is concerned with the recognition of objects. Variational methods are certainly one of the most successful methods for low-level vision. However, it is very unlikely that these methods can be further improved without the integration of high-level prior models. Therefore, we propose a unified mathematical framework that allows for a natural integration of high-level priors into low-level variational models. In particular, we propose to represent images in a higher-dimensional space which is inspired by the architecture for the visual cortex. This space performs a decomposition of the image gradients into magnitude and direction and hence performs a lifting of the 2D image to a 3D space. This has several advantages: Firstly, the higher-dimensional embedding allows to implement mid-level tasks such as boundary completion and disocclusion processes in a very natural way. Secondly, the lifted space allows for an explicit access to the orientation and the magnitude of image gradients. In turn, distributions of gradient orientations – known to be highly effective for object detection – can be utilized as high-level priors. This inverts the bottom-up nature of object detectors and hence adds an efficient top-down process to low-level variational models. The developed mathematical approaches will go significantly beyond traditional variational models for computer vision and hence will define a new state-of-the-art in the field.


year authors and title journal last update
List of publications.
2019 Antonin Chambolle, Thomas Pock
Total roto-translational variation
published pages: 611-666, ISSN: 0029-599X, DOI: 10.1007/s00211-019-01026-w
Numerische Mathematik 142/3 2020-04-07
2016 Christian Payer, Michael Pienn, Zoltán Bálint, Alexander Shekhovtsov, Emina Talakic, Eszter Nagy, Andrea Olschewski, Horst Olschewski, Martin Urschler
Automated integer programming based separation of arteries and veins from thoracic CT images
published pages: 109-122, ISSN: 1361-8415, DOI: 10.1016/
Medical Image Analysis 34 2020-04-07
2017 Christoph Vogel, Thomas Pock
A Primal Dual Network for Low-Level Vision Problems
published pages: 189-202, ISSN: , DOI: 10.1007/978-3-319-66709-6_16
German Conference on Pattern Recognition 2020-04-07
2016 Antonin Chambolle, Thomas Pock
An introduction to continuous optimization for imaging
published pages: 161-319, ISSN: 0962-4929, DOI: 10.1017/S096249291600009X
Acta Numerica 25 2020-04-07
2017 Teresa Klatzer, Daniel Soukup, Erich Kobler, Kerstin Hammernik, Thomas Pock
Trainable Regularization for Multi-frame Superresolution
published pages: 90-100, ISSN: , DOI: 10.1007/978-3-319-66709-6_8
German Conference on Pattern Recognition 2020-04-07
2016 Alexander Kirillov Alexander Shekhovtsov Carsten Rother Bogdan Savchynskyy
Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization
published pages: 1-9, ISSN: , DOI:
Advances in Neural Information Processing Systems 2020-04-07
2017 Yunjin Chen, Thomas Pock
Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
published pages: 1256-1272, ISSN: 0162-8828, DOI: 10.1109/TPAMI.2016.2596743
IEEE Transactions on Pattern Analysis and Machine Intelligence 39/6 2020-04-07
2016 Vladimir Kolmogorov, Thomas Pock, Michal Rolinek
Total Variation on a Tree
published pages: 605-636, ISSN: 1936-4954, DOI: 10.1137/15M1010257
SIAM Journal on Imaging Sciences 9/2 2020-04-07
2017 Audrey Richard, Christoph Vogel, Maros Blaha, Thomas Pock, Konrad Schindler
Semantic 3D Reconstruction with Finite Element Bases
published pages: , ISSN: , DOI:
British Machine Vision Conference (BMVC) 2020-04-07
2017 Erich Kobler, Teresa Klatzer, Kerstin Hammernik, Thomas Pock
Variational Networks: Connecting Variational Methods and Deep Learning
published pages: 281-293, ISSN: , DOI: 10.1007/978-3-319-66709-6_23
German Conference on Pattern Recognition 2020-04-07
2017 Tuomo Valkonen, Thomas Pock
Acceleration of the PDHGM on Partially Strongly Convex Functions
published pages: , ISSN: 0924-9907, DOI: 10.1007/s10851-016-0692-2
Journal of Mathematical Imaging and Vision 2020-04-07
2016 Thomas Pock, Shoham Sabach
Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems
published pages: 1756-1787, ISSN: 1936-4954, DOI: 10.1137/16M1064064
SIAM Journal on Imaging Sciences 9/4 2020-04-07
2018 Katrin Lasinger, Christoph Vogel, Thomas Pock, Konrad Schindler
Variational 3D-PIV with sparse descriptors
published pages: 64010, ISSN: 0957-0233, DOI: 10.1088/1361-6501/aab5a0
Measurement Science and Technology 29/6 2020-04-07
2017 Gottfried Munda, Alexander Shekhovtsov, Patrick Knöbelreiter, Thomas Pock
Scalable Full Flow with Learned Binary Descriptors
published pages: 321-332, ISSN: , DOI: 10.1007/978-3-319-66709-6_26
German Conference on Pattern Recognition 2020-04-07
2017 Kerstin Hammernik, Teresa Klatzer, Erich Kobler, Michael P. Recht, Daniel K. Sodickson, Thomas Pock, Florian Knoll
Learning a variational network for reconstruction of accelerated MRI data
published pages: , ISSN: 0740-3194, DOI: 10.1002/mrm.26977
Magnetic Resonance in Medicine 2020-04-07

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "HOMOVIS" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email ( and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "HOMOVIS" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.1.1.)


Forms of Labour: Gender, Freedom and Experience of Work in the Preindustrial Economy

Read More  

PrISMoID (2019)

Photonic Structural Materials with Controlled Disorder

Read More  

U-HEART (2018)

Unbreakable HEART: a reconfigurable and self-healing isolated dc/dc converter (U-HEART)

Read More